Extraction of Fetal ECG Signal with Ectopic Beats using Blind Source Separation Based Null Space Approach

Abstract

The aim of this paper is to apply blind source separation (BSS) to extract fetal electrocardiogram (FECG) signal with ectopic beat. We use a novel deterministic BSS algorithm type null space transformation matrix (NSITM). The ECG signals are used to compute the ITM. Then, the FECG signal and maternal ECG (MECG) signals are extracted from the null space of the ITM. Results from Physionet synthesized ECG data show considerable improvement in extraction performance (quality signal-to-noise ratio qSNR and correlation $r$) over other algorithms used in this work, when the fetal-to-maternal signal-to-noise ratio (fmSNR) increases from −30 dB to 0 dB. Using the NSITM algorithm, the maximum values of qSNR and $r$ are 5.95 dB and 0.871, respectively, when fmSNR is equal to 0 dB. The minimum values of qSNR and $r$ are 2.27 dB and 0.726, respectively, when fmSNR is equal to −30 dB. The study demonstrates that the BSS type NSITM is a feasible algorithm for extracting FECG signals for subjects with ectopic beats.